Jun Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jun Ma has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Maarten de Rijke
University of Amsterdam, Amsterdam, Netherlands
2 shared publications - Pengjie Ren
Shandong University, Qingdao, China
2 shared publications - Shuaiqiang Wang
Baidu Inc., Beijing, China
2 shared publications - Zhumin Chen
School of Artificial Intelligence, Shandong University, Jinan, Shandong, China
2 shared publications - Andrew T. Young
Texas Tech University
1 shared publication - Beverly S. Bunch
University of Illinois at Springfield
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Wiley in Journal of Diabetes Research
- Vol. 2025 (1) , 4586856
Alterations in Corneal Nerve Structure and Function in Prediabetes
Background: Although prediabetes increases the risk of developing diabetes, its role in neuropathy remains unclear. We aim to assess alterations in the corneal nerve structure and function in prediabetes and risk factors for corneal nerve loss. Methods: An examination of IVCM and corneal sensitivity was conducted on a cohort of 75 participants, comprising 23 controls, 32 prediabetes, and 20 Type 2 diabetes. Semiautomatic analysis was employed to quantify the corneal nerve fiber length (CNFL), corneal nerve fiber density (CNFD), and dendritic cell (DC) density. Results: CNFL and CNFD were lower in prediabetes and Type 2 diabetes than in the controls, and they were associated with DC density. CNFL and CNFD were lower in Type 2 diabetes than in prediabetes. DC density was higher in prediabetes and Type 2 diabetes than in controls. However, there were no differences in corneal sensitivity between controls and prediabetes. Multivariable regression analysis demonstrated an association between reduced CNFL and age, BMI, fasting plasma glucose (FPG), and uric acid (UA) levels in prediabetes. In Type 2 diabetes, age, HbA1c, blood urea nitrogen (BUN), creatinine (Cr), and triglyceride levels exhibited associations with reduced CNFL. Conclusions: Corneal nerve damage was detected in prediabetes using IVCM. The patients with prediabetes showed signs of nerve structure damage, and the corneal nerve structure damage occurred before the nerve function changes. Immune cells also participate in the occurrence and development of DCN and are related to the corneal neuropathy. Understanding the corneal nerve fiber condition through IVCM may prove crucial in monitoring prediabetic neuropathy.
- 1 January 2025
- Published by Wiley in Journal of Diabetes Research
- Vol. 2025 (1) , 4586856
Open AccessAlterations in Corneal Nerve Structure and Function in Prediabetes
Background: Although prediabetes increases the risk of developing diabetes, its role in neuropathy remains unclear. We aim to assess alterations in the corneal nerve structure and function in prediabetes and risk factors for corneal nerve loss. Methods: An examination of IVCM and corneal sensitivity was conducted on a cohort of 75 participants, comprising 23 controls, 32 prediabetes, and 20 Type 2 diabetes. Semiautomatic analysis was employed to quantify the corneal nerve fiber length (CNFL), corneal nerve fiber density (CNFD), and dendritic cell (DC) density. Results: CNFL and CNFD were lower in prediabetes and Type 2 diabetes than in the controls, and they were associated with DC density. CNFL and CNFD were lower in Type 2 diabetes than in prediabetes. DC density was higher in prediabetes and Type 2 diabetes than in controls. However, there were no differences in corneal sensitivity between controls and prediabetes. Multivariable regression analysis demonstrated an association between reduced CNFL and age, BMI, fasting plasma glucose (FPG), and uric acid (UA) levels in prediabetes. In Type 2 diabetes, age, HbA1c, blood urea nitrogen (BUN), creatinine (Cr), and triglyceride levels exhibited associations with reduced CNFL. Conclusions: Corneal nerve damage was detected in prediabetes using IVCM. The patients with prediabetes showed signs of nerve structure damage, and the corneal nerve structure damage occurred before the nerve function changes. Immune cells also participate in the occurrence and development of DCN and are related to the corneal neuropathy. Understanding the corneal nerve fiber condition through IVCM may prove crucial in monitoring prediabetic neuropathy.
- Open Access
- 7 September 2022
- Published by Wiley in Public Budgeting & Finance
- Vol. 42 (3) , 1-2
Issue Information
- 7 September 2022
- Published by Wiley in Public Budgeting & Finance
- Vol. 42 (3) , 1-2
Open AccessIssue Information
- Open Access
RefNet: A Reference-aware Network for Background Based Conversation
Existing conversational systems tend to generate generic responses. Recently, Background Based Conversations (BBCs) have been introduced to address this issue. Here, the generated responses are grounded in some background information. The proposed methods for BBCs are able to generate more informative responses, they either cannot generate natural responses or have difficulty in locating the right background information. In this paper, we propose a Reference-aware Network (RefNet) to address the two issues. Unlike existing methods that generate responses token by token, RefNet incorporates a novel reference decoder that provides an alternative way to learn to directly cite a semantic unit (e.g., a span containing complete semantic information) from the background. Experimental results show that RefNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, indicating that RefNet can generate more appropriate and human-like responses.
Open AccessRefNet: A Reference-aware Network for Background Based Conversation
Existing conversational systems tend to generate generic responses. Recently, Background Based Conversations (BBCs) have been introduced to address this issue. Here, the generated responses are grounded in some background information. The proposed methods for BBCs are able to generate more informative responses, they either cannot generate natural responses or have difficulty in locating the right background information. In this paper, we propose a Reference-aware Network (RefNet) to address the two issues. Unlike existing methods that generate responses token by token, RefNet incorporates a novel reference decoder that provides an alternative way to learn to directly cite a semantic unit (e.g., a span containing complete semantic information) from the background. Experimental results show that RefNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, indicating that RefNet can generate more appropriate and human-like responses.
- Open Access
RepeatNet: A Repeat Aware Neural Recommendation Machine for Session-based Recommendation
Recurrent neural networks for session-based recommendation have attracted a lot of attention recently because of their promising performance. repeat consumption is a common phenomenon in many recommendation scenarios (e.g., e-commerce, music, and TV program recommendations), where the same item is re-consumed repeatedly over time. However, no previous studies have emphasized repeat consumption with neural networks. An effective neural approach is needed to decide when to perform repeat recommendation. In this paper, we incorporate a repeat-explore mechanism into neural networks and propose a new model, called RepeatNet, with an encoder-decoder structure. RepeatNet integrates a regular neural recommendation approach in the decoder with a new repeat recommendation mechanism that can choose items from a user's history and recommends them at the right time. We report on extensive experiments on three benchmark datasets. RepeatNet outperforms state-of-the-art baselines on all three datasets in terms of MRR and Recall. Furthermore, as the dataset size and the repeat ratio increase, the improvements of RepeatNet over the baselines also increase, which demonstrates its advantage in handling repeat recommendation scenarios.
Open AccessRepeatNet: A Repeat Aware Neural Recommendation Machine for Session-based Recommendation
Recurrent neural networks for session-based recommendation have attracted a lot of attention recently because of their promising performance. repeat consumption is a common phenomenon in many recommendation scenarios (e.g., e-commerce, music, and TV program recommendations), where the same item is re-consumed repeatedly over time. However, no previous studies have emphasized repeat consumption with neural networks. An effective neural approach is needed to decide when to perform repeat recommendation. In this paper, we incorporate a repeat-explore mechanism into neural networks and propose a new model, called RepeatNet, with an encoder-decoder structure. RepeatNet integrates a regular neural recommendation approach in the decoder with a new repeat recommendation mechanism that can choose items from a user's history and recommends them at the right time. We report on extensive experiments on three benchmark datasets. RepeatNet outperforms state-of-the-art baselines on all three datasets in terms of MRR and Recall. Furthermore, as the dataset size and the repeat ratio increase, the improvements of RepeatNet over the baselines also increase, which demonstrates its advantage in handling repeat recommendation scenarios.
- Open Access
- 29 October 2012
- Published by Association for Computing Machinery (ACM)
- Vol. 6, 2423-2426
Semantically coherent image annotation with a learning-based keyword propagation strategy
- 29 October 2012
- Published by Association for Computing Machinery (ACM)
- Vol. 6, 2423-2426
Open AccessSemantically coherent image annotation with a learning-based keyword propagation strategy
- 1 October 2010
- Published by Elsevier in Information Sciences
- Vol. 180 (20) , 3894-3913
Formal behavior modeling and effective automatic refinement
- 1 October 2010
- Published by Elsevier in Information Sciences
- Vol. 180 (20) , 3894-3913
Formal behavior modeling and effective automatic refinement
- Open Access
- 1 May 2010
- Published by Elsevier in Expert Systems with Applications
- Vol. 37 (5) , 3737-3746
Collaborative management of web ontology data with flexible access control
- 1 May 2010
- Published by Elsevier in Expert Systems with Applications
- Vol. 37 (5) , 3737-3746
Open AccessCollaborative management of web ontology data with flexible access control
- 9 July 2008
- Published by China Science Publishing & Media Ltd. in Journal of Software
- Vol. 19 (2) , 267-274
Classification of Deep Web Databases Based on the Context of Web Pages
- 9 July 2008
- Published by China Science Publishing & Media Ltd. in Journal of Software
- Vol. 19 (2) , 267-274
Classification of Deep Web Databases Based on the Context of Web Pages